{"id":"https://openalex.org/W4416157220","doi":"https://doi.org/10.1145/3798129.3800926","title":"Sparse Linear Regression Is Easy on Random Supports","display_name":"Sparse Linear Regression Is Easy on Random Supports","publication_year":2026,"publication_date":"2026-06-09","ids":{"openalex":"https://openalex.org/W4416157220","doi":"https://doi.org/10.1145/3798129.3800926"},"language":null,"primary_location":{"id":"doi:10.1145/3798129.3800926","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3798129.3800926","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 58th Annual ACM Symposium on Theory of Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3798129.3800926","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113253022","display_name":"Gautam Chandrasekaran","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gautam Chandrasekaran","raw_affiliation_strings":["University of Texas at Austin, Austin, USA"],"raw_orcid":"https://orcid.org/0009-0002-2443-8675","affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044675813","display_name":"Raghu Meka","orcid":"https://orcid.org/0009-0004-7676-2762"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghu Meka","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0009-0004-7676-2762","affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120396383","display_name":"Konstantinos Stavropoulos","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Konstantinos Stavropoulos","raw_affiliation_strings":["University of Texas at Austin, Austin, USA"],"raw_orcid":"https://orcid.org/0009-0006-2643-4298","affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01043215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2242","last_page":"2253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.8213000297546387,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.8213000297546387,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.07859999686479568,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.02280000038444996,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5881999731063843},{"id":"https://openalex.org/keywords/design-matrix","display_name":"Design matrix","score":0.5792999863624573},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5400999784469604},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5281000137329102},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4984999895095825},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.4787999987602234},{"id":"https://openalex.org/keywords/random-matrix","display_name":"Random matrix","score":0.47699999809265137},{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.3928000032901764}],"concepts":[{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5881999731063843},{"id":"https://openalex.org/C203233044","wikidata":"https://www.wikidata.org/wiki/Q5264358","display_name":"Design matrix","level":3,"score":0.5792999863624573},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5400999784469604},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5281000137329102},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5163000226020813},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4984999895095825},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48330000042915344},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.4787999987602234},{"id":"https://openalex.org/C64812099","wikidata":"https://www.wikidata.org/wiki/Q176604","display_name":"Random matrix","level":3,"score":0.47699999809265137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3961000144481659},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.392300009727478},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37700000405311584},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C55974624","wikidata":"https://www.wikidata.org/wiki/Q1188504","display_name":"Exponential family","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.30790001153945923},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.2924000024795532},{"id":"https://openalex.org/C75235859","wikidata":"https://www.wikidata.org/wiki/Q582659","display_name":"Exponential growth","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.28040000796318054},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26570001244544983},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.265500009059906},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2538999915122986}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3798129.3800926","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3798129.3800926","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 58th Annual ACM Symposium on Theory of Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.06211","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.06211","pdf_url":"https://arxiv.org/pdf/2511.06211","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.06211","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.06211","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3798129.3800926","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3798129.3800926","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 58th Annual ACM Symposium on Theory of Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1556686326","display_name":null,"funder_award_id":"CCF-2217033","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1610805586","display_name":null,"funder_award_id":"CCF-2505865","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Sparse":[0],"linear":[1],"regression":[2],"is":[3,45,63,72,81,103,147,166,198],"one":[4],"of":[5,108,196],"the":[6,46,49,54,58,76,152,157,177,194],"most":[7,111,121],"basic":[8],"questions":[9],"in":[10,48,106,261],"machine":[11],"learning":[12],"and":[13,29,43,159,172,215],"statistics.":[14],"Here,":[15],"we":[16,52,100,115,141,160,190,202],"are":[17],"given":[18],"as":[19,259],"input":[20],"a":[21,84,252],"design":[22,184,223,244],"matrix":[23,224],"X":[24,39,97,225],"\u2208":[25,34],"\u211dN":[26,35],"\u00d7":[27],"d":[28],"measurements":[30],"or":[31,264],"labels":[32],"y":[33,37],"where":[36,70],"=":[38,126,139,210],"w*":[40,62,95,197],"+":[41],"\u03be,":[42],"\u03be":[44],"noise":[47,113],"measurements.":[50],"Importantly,":[51],"have":[53,251],"additional":[55],"constraint":[56],"that":[57,88,192,250],"unknown":[59],"signal":[60],"vector":[61,86],"sparse:":[64],"it":[65,165],"has":[66,89],"k":[67,71],"non-zero":[68],"entries":[69],"much":[73],"smaller":[74],"than":[75],"ambient":[77],"dimension.":[78],"Our":[79],"goal":[80],"to":[82,168,230],"output":[83],"prediction":[85,91,118,205],"w":[87],"small":[90],"error:":[92],"1/N\u00b7":[93],"||X":[94],"\u2212":[96],"w||22.":[98],"Information-theoretically,":[99],"know":[101,163],"what":[102],"best":[104],"possible":[105,167],"terms":[107],"measurements:":[109],"under":[110],"natural":[112],"distributions,":[114],"can":[116,142,203],"get":[117,143,169,204],"error":[119,206],"at":[120,200],"\u0454":[122,207],"with":[123,137,208,226,266],"roughly":[124],"N":[125,138,209],"O(k":[127],"logd/\u0454)":[128],"samples.":[129,174],"Computationally,":[130],"this":[131],"currently":[132],"needs":[133],"d\u03a9(k)":[134],"run-time.":[135],"Alternately,":[136],"O(d),":[140],"polynomial-time.":[144],"Thus,":[145],"there":[146],"an":[148],"exponential":[149],"gap":[150],"(in":[151],"dependence":[153],"on":[154],"d)":[155],"between":[156],"two":[158],"do":[161],"not":[162],"if":[164,193],"do(k)":[170],"run-time":[171,216,219],"o(d)":[173],"We":[175],"give":[176],"first":[178],"generic":[179],"positive":[180],"result":[181],"for":[182,221,237,242],"worst-case":[183,238],"matrices":[185,245,249],"X:":[186],"For":[187],"any":[188,222],"X,":[189],"show":[191],"support":[195],"chosen":[199],"random,":[201],"poly(k,":[211],"logd,":[212],"1/\u0454)":[213],"samples":[214],"poly(d,N).":[217],"This":[218],"holds":[220],"condition":[227,255],"number":[228,256],"up":[229],"2poly(d).":[231],"Previously,":[232],"such":[233],"results":[234],"were":[235],"known":[236],"w*,":[239],"but":[240],"only":[241],"random":[243],"from":[246],"well-behaved":[247],"families,":[248],"very":[253],"low":[254],"(poly(logd);":[257],"e.g.,":[258],"studied":[260],"compressed":[262],"sensing),":[263],"those":[265],"special":[267],"structural":[268],"properties.":[269]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-12T00:00:00"}